© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47647
    Prev
    Next
    INDEX
    Explanations

    awards for gallantry or meritorious service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    å¼ĢæĿ¥
    -0.10
    é«ĺ涨
    -0.09
    TYPO
    -0.08
    ä¸į好
    -0.08
    ä½ĵæ£Ģ
    -0.08
    çĤ¬
    -0.08
     Satellite
    -0.08
    就没
    -0.08
    etes
    -0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    POSITIVE LOGITS
    æ»Ĥ
    0.09
    cona
    0.09
    è¥
    0.09
    æĹĹä¸ĭ
    0.09
    markt
    0.09
     deed
    0.08
    _criteria
    0.08
    burger
    0.08
    æĩĴ
    0.08
    è¢ľ
    0.08
    Activations Density 0.017%

    No Known Activations